The paper introduces Speech-Rewarded Style Planning (SRSP), a method that trains a text-based style planner using a frozen downstream TTS model. SRSP generates candidate style instructions from dialogue history and response text, optimizing them with group-relative policy optimization (GRPO) where the reward is the teacher‑forced likelihood of target speech tokens. Experiments on an English subset of the ISCSLP 2026 CoT‑TTS corpus show that SRSP outperforms baseline LLM and target‑audio‑informed captioning approaches in speech‑style and emotion similarity, mel‑cepstral distortion, and contextual appropriateness. "whyItMatters":"The study demonstrates a more effective way to align natural‑language style descriptions with actual acoustic output, improving controllability and fidelity in conversational text‑to‑speech systems."
arXiv:2606. 20532v1 Announce Type: new Abstract: Style-captioned text-to-speech systems use natural language to control voice characteristics, but how individual words influence acoustic output remains unclear.
arXiv:2609.22697v1 Announce Type: new Abstract: Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated...
arXiv:2609.01246v1 Announce Type: new Abstract: Current Large Language Models (LLMs) are primarily optimized for written text, often producing outputs that are grammatically correct and helpful yet p...
The paper introduces a method called randomized intermediate guidance for training tandem speech-to-speech models, where a large language model (LLM) acts as a backend providing candidate responses while the user is speaking. Instead of simulating the backend’s guidance, the approach derives guidance directly from the conversation corpus, using target responses for informative guidance and randomly sampled responses to simulate irrelevant updates. Experiments on synthetic dialogues and 3.8k hours of real conversations show that this technique yields response quality comparable to LLM-generated baselines while improving natural turn‑taking and audio‑judge naturalness.
arXiv:2510.22588v2 Announce Type: replace-cross Abstract: Spoken dialogue models currently lack the ability for fine-grained speech style control, a critical capability for human-like interaction tha...
arXiv:2606. 26534v1 Announce Type: cross Abstract: Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styles from uncommon scenarios (e.
arXiv:2606. 07387v1 Announce Type: new Abstract: State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages.
arXiv:2512. 20978v2 Announce Type: replace-cross Abstract: Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech.
arXiv:2609.15313v1 Announce Type: cross Abstract: Autoregressive generation of interleaved text and acoustic tokens is a common approach to spoken-response generation in speech large language models....
arXiv:2606. 19325v1 Announce Type: cross Abstract: Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings.
EmphTTS is a non‑autoregressive text‑to‑speech system that uses Group Relative Policy Optimization (GRPO) to train its duration predictor with an emphasis localization reward, allowing direct word‑level emphasis control. The system outperforms existing baselines in both objective emphasis evaluation and subjective preference tests, and ablation studies confirm that GRPO improves emphasis realization while reducing mismatch between the duration predictor and the TTS model.
The paper introduces ReACT‑TTS, a two‑stage framework that uses a one‑second sequence of listener facial reactions to plan the emotion and prosody of a conversational utterance before speech synthesis. Experiments on the MELD dataset show that temporally conditioned models outperform text‑only baselines in macro‑F1 and VAD concordance, while accuracy remains unchanged. A contextual‑appropriateness study with speech researchers indicates a strong preference for temporally conditioned responses, and the approach is integrated with a Grad‑TTS backbone for end‑to‑end speech generation.